How to use OpenAI Codex via MCP tools for code generation, plan review, and collaborative implementation loops. Use when calling Codex for implementation, review, or any cross-model collaboration.
Langue du texte source : anglais
Menu
SkillsMP a collecté 8 skills depuis dkorduban/twilight-struggle-ai. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 8 skills collectés sur 8.
How to use OpenAI Codex via MCP tools for code generation, plan review, and collaborative implementation loops. Use when calling Codex for implementation, review, or any cross-model collaboration.
Langue du texte source : anglais
Master task dispatcher. Simple tasks (≤2 files, ≤30 lines, clear spec) are done inline by the main agent. Complex tasks are routed to bg-codex-implementer as a background agent. Triggers on: /dispatch, implement this, fix this, debug this, dispatch task.
Langue du texte source : anglais
Benchmark one or more model checkpoints (2000 games/side) with auto-logging. Triggers on: /bench, benchmark this model, run benchmark, bench checkpoint.
Langue du texte source : anglais
Analyze a slow process, identify bottleneck, write spec, delegate optimization to Codex. Triggers on: /speedup-analysis, speed this up, optimize performance, this is too slow, why is this slow.
Langue du texte source : anglais
Chain training → export → benchmark as one background pipeline. Triggers on: /train-and-bench, train and benchmark, run training pipeline, train this model.
Langue du texte source : anglais
Full system status: background tasks, running processes, GPU/CPU/memory utilization, lock files. Triggers on: /check-tasks, /status, task status, what's running, system status, check background.
Langue du texte source : anglais
Batch 5-20 rules/card questions into one Haiku agent call that reads PDF + docs once and answers all. Replaces per-question rules-lawyer calls. Triggers on: /rules-batcher, batch rules questions, look up these cards, verify these rules.
Langue du texte source : anglais
Explore codebase with Haiku, synthesize a tight machine-readable implementation spec. Output feeds directly into /feature-coder or /tdd-fixer — no plan-audit loop. Triggers on: /spec-writer, write a spec, spec out this feature, spec before coding.
Langue du texte source : anglais